Legal claims defining the scope of protection, as filed with the USPTO.
1. A method of generating a link in an image, comprising the steps of: a) inputting the image containing segments; b) dividing the image into segments, said segments containing at least one figure portion and at least one text portion, said figure portion and said text portion further containing a reference area; c) determining said reference area among said segments by selecting reference candidates for said reference area and comparing each of said reference candidates to said figure portion of the image; d) recognizing characters in the image including said reference area; and e) generating a link between said reference area of said figure portion and a corresponding one of said text portion based upon said characters.
2. The method of generating a link in an image according to claim 1 wherein said step g) further comprises steps of: h) determining whether a size of said reference candidates is within a predetermined font size; i) determining whether a distance between each of said reference candidates and said figure portion is within a predetermined distance; and j) determining whether an amount of misalignment of said figure portion is within a predetermined error amount.
3. The method of generating a link in an image according to claim 1 wherein said step g) further comprises steps of: k) determining whether each of said reference candidates is near a text portion; l) determining whether a distance between each of said text portions and said figure portion is within a predetermined distance; and m) said selecting one of said reference candidates that is closer to said text portion than figure portion.
4. The method of generating a link in an image according to claim 1 wherein the figure portion includes a figure, a graph, an equation and a table.
5. A system for generating a link in an image between a figure portion and a corresponding text portion, comprising: an inputting unit for inputting the image; a segmentation unit connected to said inputting unit for dividing the image into segments, said segments containing at least one figure portion and at least one text portion, said figure portion and said text portion further containing a reference area; a reference area determination unit connected to said segmentation unit for determining said reference area among said segments, said reference area determination unit further selecting reference candidates for said reference area and comparing each of said reference candidates to said figure portion of the image; a character recognition unit connected to said inputting unit for recognizing characters in the image including said reference area; and a link generation unit connected to said reference area determination unit and said character recognition unit for generating a link between said reference area of said figure portion and a corresponding one of said text portion based upon said characters.
6. The system for generating a link in an image according to claim 5 wherein said reference area determination unit determines whether a size of said reference candidates is within a predetermined font size.
7. The system for generating a link in an image according to claim 5 wherein said reference area determination unit determines whether a distance between each of said reference candidates and said figure portion is within a predetermined distance.
8. The system for generating a link in an image according to claim 5 wherein said reference area determination unit determines whether an amount of misalignment of said figure portion is within a predetermined error amount.
9. The system for generating a link in an image according to claim 5 wherein said reference area determination unit determines whether each of said reference candidates is near a text portion.
10. The system for generating a link in an image according to claim 9 wherein said reference area determination unit determines selects one of said reference candidates that is closer to said text portion than said figure portion.
11. The system for generating a link in an image according to claim 5 wherein the figure portion includes a figure, a graph, an equation and a table.
Complete technical specification and implementation details from the patent document.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT(S)
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
Unknown
January 23, 2001
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.